Back to search
mcp-schema-fuzzer
MCP serverGitHub
Zero-dependency Python CLI that validates Model Context Protocol (MCP) JSON-RPC tool schemas and runs boundary/type fuzz tests against local stdio/HTTP MCP servers.
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Checked today
Badge for your README
Markdown
[](/listings/dungfundopt--mcp-schema-fuzzer)HTML
<a href="/listings/dungfundopt--mcp-schema-fuzzer"><img src="/api/listings/dungfundopt--mcp-schema-fuzzer/badge.svg" alt="findsafeskills safety rating" /></a>Install
i
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
1. Clone this repository 2. Ensure you have Python 3.10+ 3. Make the CLI executable (optional):
chmod +x cli.py
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 100 lines
- # MCP Schema Fuzzer
- A zero-dependency Python CLI tool for validating Model Context Protocol (MCP) JSON-RPC schemas and running boundary/type fuzz tests against local stdio or HTTP servers.
- ## Features
- - Validate MCP JSON-RPC schemas
- - Generate fuzz test cases based on schema definitions
- - Test against local stdio or remote HTTP servers
- - Pure Python implementation (no third-party dependencies)
- ## Installation
- 1. Clone this repository
- 2. Ensure you have Python 3.10+
- 3. Make the CLI executable (optional):
- ```bash
- chmod +x cli.py
- ```
- ## Usage
- ### Basic Validation
- ```bash
- python cli.py path/to/schema.json
- ```
- ### Testing Against a Server
- ```bash
- python cli.py path/to/schema.json --server http://localhost:8000/api
- ```
- ### Custom Test Count
- ```bash
- python cli.py path/to/schema.json --count 20
- ```
- ### Save Results to File
- ```bash
- python cli.py path/to/schema.json --output results.json
- ```
- ## Schema Format
- The tool expects a JSON schema in the following format:
- ```json
- {
- "type": "object",
- "properties": {
- "field1": {
- "type": "string",
- "minLength": 1,
- "maxLength": 100
- },
- "field2": {
- "type": "integer",
- "minimum": 0,
- "maximum": 100
- }
- },
- "required": ["field1"]
- }
- ```
- ## Example Output
- ```json
- [
- {
- "input": {
- "name": "Test User",
- "age": 30,
- "active": true
- },
- "status": "valid"
- },
- {
- "input": {
- "name": "",
- "age": 150
- },
- "errors": [
- "Field name must have minimum length of 1",
- "Field age must be less than or equal to 120"
- ],
- "status": "invalid"
- }
- ]
- ```
- ## Development
- Run tests with:
- ```bash
- python -m unittest test_cli.py
- ```
- ## License
- MIT License
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.